fishead

fishead's Stars

• oobabooga/text-generation-webui

  A Gradio web UI for Large Language Models with support for multiple inference backends.

  Language:Python41.7k5.4k

• QwenLM/Qwen2.5

  Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

  Language:Shell11.8k708

• juliansteenbakker/mobile_scanner

  A universal scanner for Flutter based on MLKit. Uses CameraX on Android and AVFoundation on iOS.

  Language:Dart934530

• FlagOpen/FlagEmbedding

  Retrieval and Retrieval-augmented LLMs

  Language:Python8.3k604

• BerriAI/litellm

  Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

  Language:Python16.3k1.9k

• SylphAI-Inc/AdalFlow

  AdalFlow: The library to build & auto-optimize LLM applications.

  Language:Python2.5k221

• stanfordnlp/dspy

  DSPy: The framework for programming—not prompting—language models

  Language:Python21.1k1.6k

• zou-group/textgrad

  TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

  Language:Python2k170

• rrousselGit/riverpod

  A reactive caching and data-binding framework. Riverpod makes working with asynchronous code a breeze.

  Language:Dart6.4k970

• gusye1234/nano-graphrag

  A simple, easy-to-hack GraphRAG implementation

  Language:Python2.1k202

• HKUDS/LightRAG

  "LightRAG: Simple and Fast Retrieval-Augmented Generation"

  Language:Python11.2k1.5k

• Whisky-App/Whisky

  A modern Wine wrapper for macOS built with SwiftUI

  Language:Swift13.5k291

• utmapp/UTM

  Virtual machines for iOS and macOS

  Language:Swift27.8k1.4k

• iamkun/dayjs

  ⏰ Day.js 2kB immutable date-time library alternative to Moment.js with the same modern API

  Language:JavaScript47.3k2.3k

• karpathy/nanoGPT

  The simplest, fastest repository for training/finetuning medium-sized GPTs.

  Language:Python38.5k6.3k

• dottxt-ai/outlines

  Structured Text Generation

  Language:Python10.4k543

• Mirascope/mirascope

  LLM abstractions that aren't obstructions

  Language:Python86860

• fastapi-users/fastapi-users

  Ready-to-use and customizable users management for FastAPI

  Language:Python4.8k399

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++70.9k10.3k

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++9.2k1.1k

• InternLM/lmdeploy

  LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

  Language:Python5.2k463

• DAGWorks-Inc/burr

  Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

  Language:Python1.4k76

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python33.9k5.2k

• open-webui/open-webui

  User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

  Language:JavaScript57k7.1k

• immortalwrt/homeproxy

  The modern ImmortalWrt proxy platform for ARM64/AMD64 (powered by sing-box)

  Language:JavaScript616201

• fengyuan-liang/deploy-certificate-to-aliyun

  每两个月自动部署泛解析证书到阿里云CDN上

  Language:Python2024

• tj/git-extras

  GIT utilities -- repo summary, repl, changelog population, author commit percentages and more

  Language:Shell17.5k1.2k

• vikejs/vike-react

  🔨 React integration for Vike

  Language:TypeScript11419

• microsoft/graphrag

  A modular graph-based Retrieval-Augmented Generation (RAG) system

  Language:Python21.7k2.1k

• k3s-io/k3s

  Lightweight Kubernetes

  Language:Go28.6k2.4k